Skip to main content
Glama

Check flight compensation

check_flight_compensation
Read-only

Check whether an airline owes cash compensation for a delayed or cancelled flight under Canada's Air Passenger Protection Regulations, and how much. Ask the passenger for every answer; don't guess. Returns the verdict, amount per passenger and the last day to file. General information, not legal advice.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "disruption": "<disruption>",
      "originIata": "<originIata>",
      "destinationIata": "<destinationIata>",
      "marketingCarrierIata": "<marketingCarrierIata>",
      "charter": "<charter>",
      "flightDate": "<flightDate>",
      "outcome": "<outcome>",
      "notice": "<notice>",
      "reason": "<reason>",
      "blamedEarlierFlight": "<blamedEarlierFlight>",
      "acceptedVoucherInWriting": "<acceptedVoucherInWriting>",
      "alreadyCompensated": "<alreadyCompensated>"
    },
    "name": "check_flight_compensation"
  }
}

Input Schema

NameRequiredDescriptionDefault
noticeYesWhen did the airline tell the passenger? "within_14_days" includes being told at the airport.
reasonYesThe reason the airline gave, mapped to the closest value. Airline operations: crew_shortage (Crew or staff shortage), scheduled_maintenance (Scheduled maintenance), schedule_or_aircraft_change (Schedule change or aircraft swap), airline_it_problem (Airline's computer or IT problem). Safety: mechanical_issue (Mechanical or technical problem), safety_other (Another safety reason). Outside the airline: weather (Weather), air_traffic_control (Air traffic control), airport_operations (Airport problem (e.g. de-icing, runway, fuelling)), security_threat (Security threat), medical_emergency (Medical emergency), wildlife_strike (Bird or wildlife strike), labour_disruption (Strike or labour disruption), manufacturer_defect (Aircraft defect announced by the manufacturer or regulator), government_or_police_order (Order from government, police or airport security), war_or_unrest (War or political unrest), illegal_act (Sabotage or another illegal act). Not sure: no_reason_given (They didn't give a clear reason), not_remembered (I don't remember), other (Something else).
charterYesWas it a charter or package-holiday flight? Use "unsure" if the passenger does not know.
outcomeYes"travelled" = reached the destination (original or new flight); "refunded" = took a refund instead; "other" = e.g. made their own way.
disruptionYesWas the flight delayed or cancelled?
flightDateYesOriginal scheduled departure date, YYYY-MM-DD.
originIataYesIATA code of the departure airport, e.g. YYZ. Use find_airport if unsure.
arrivalDelayNoIf the passenger doesn't know the exact times: how late they reached the final destination. When outcome is "travelled", give scheduledArrival + actualArrival, or this.
actualArrivalNoWhen the passenger actually arrived at the final destination (aircraft door opened), local time there: YYYY-MM-DDTHH:mm.
connectionIatasNoIATA codes of connecting airports, in order. Empty for a direct flight.
destinationIataYesIATA code of the FINAL destination on the original ticket (not a connection).
scheduledArrivalNoScheduled arrival at the final destination, as on the original ticket, local time there: YYYY-MM-DDTHH:mm. With actualArrival; or use arrivalDelay instead.
alreadyCompensatedYesHas the passenger already been paid compensation for this disruption (by the airline or under another country's rules)?
blamedEarlierFlightYesDid the airline say the problem was caused by an earlier flight?
marketingCarrierIataYes2-character code of the airline on the ticket: the letters of the flight number, e.g. AC for AC 857.
operatingCarrierIataNoOnly if a different airline actually flew the plane ("operated by ..."): its 2-character code.
delayAtRefundAtLeast3hNoOnly for a delayed flight where the passenger took a refund: was it at least 3 hours late at that point?
acceptedVoucherInWritingYesDid the passenger accept a voucher or credit instead of cash, in writing?

Output Schema

NameRequiredDescriptionDefault
verdictYes
moreInfoYes
whyNotOwedYes
amountCadMaxYes
amountCadMinYes
deadlineSoonYes
whereToClaimYes
lastDayToFileYes
euOrUkRulesMayAlsoApplyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedOutput schema / properties / whyNotOwed
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "verdict",
      -  "amountCadMin",
      -  "amountCadMax",
      -  "lastDayToFile",
      -  "deadlineSoon",
      -  "euOrUkRulesMayAlsoApply",
      -  "whereToClaim",
      -  "moreInfo"
      -]New value: +[
      +  "verdict",
      +  "amountCadMin",
      +  "amountCadMax",
      +  "lastDayToFile",
      +  "deadlineSoon",
      +  "euOrUkRulesMayAlsoApply",
      +  "whereToClaim",
      +  "whyNotOwed",
      +  "moreInfo"
      +]
  2. Changed4 schema fields changed
    • changedInput schema / properties / actualArrival / description
      Previous value: -"Required if outcome is \"travelled\": when the passenger actually arrived at the final destination (aircraft door opened), local time there: YYYY-MM-DDTHH:mm."New value: +"When the passenger actually arrived at the final destination (aircraft door opened), local time there: YYYY-MM-DDTHH:mm."
    • addedInput schema / properties / arrivalDelay
      Added value: +{
      +  "description": "If the passenger doesn't know the exact times: how late they reached the final destination. When outcome is \"travelled\", give scheduledArrival + actualArrival, or this.",
      +  "enum": [
      +    "under_3h",
      +    "3_to_6h",
      +    "6_to_9h",
      +    "9h_plus"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / scheduledArrival / description
      Previous value: -"Scheduled arrival at the final destination, as on the original ticket, local time there: YYYY-MM-DDTHH:mm."New value: +"Scheduled arrival at the final destination, as on the original ticket, local time there: YYYY-MM-DDTHH:mm. With actualArrival; or use arrivalDelay instead."
    • changedInput schema / required
      Previous value: -[
      -  "disruption",
      -  "originIata",
      -  "destinationIata",
      -  "marketingCarrierIata",
      -  "charter",
      -  "flightDate",
      -  "scheduledArrival",
      -  "outcome",
      -  "notice",
      -  "reason",
      -  "blamedEarlierFlight",
      -  "acceptedVoucherInWriting",
      -  "alreadyCompensated"
      -]New value: +[
      +  "disruption",
      +  "originIata",
      +  "destinationIata",
      +  "marketingCarrierIata",
      +  "charter",
      +  "flightDate",
      +  "outcome",
      +  "notice",
      +  "reason",
      +  "blamedEarlierFlight",
      +  "acceptedVoucherInWriting",
      +  "alreadyCompensated"
      +]
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a read-only, non-destructive, closed-world computation, so the bar is lower, and the description still adds real context: it is an advisory estimator whose reliability is bounded ('General information, not legal advice') and it returns a filing deadline as well as a verdict and per-passenger amount. It stops short of saying whether the verdict is deterministic or what happens when inputs are ambiguous (e.g. reason='not_remembered'), which is the main behavioral gap for a rule-engine tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the purpose, then the input discipline, then the return shape and disclaimer. Every sentence carries distinct information and there is no restatement of the name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 18-parameter, 12-required regulatory calculation with an output schema, the description covers what is computed, how it returns, and the input-provenance rule, leaving field mechanics to the rich schema. It could do slightly more on scope limits (non-Canadian itineraries, charter handling) to be fully self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already carries long enum glosses and format patterns, so the baseline would be 3. The description still earns above baseline by adding a cross-cutting input rule — every answer must come from the passenger, never inferred — which is semantics about the parameters that no individual schema field states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Check whether an airline owes cash compensation'), pins the legal regime (Canada's Air Passenger Protection Regulations), and states the second output dimension ('and how much'). Nothing about this overlaps with the sibling lookup tools find_airline and find_airport, so an agent can route correctly on name and description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Ask the passenger for every answer; don't guess' is an explicit procedural instruction that tells the agent how to gather input rather than fabricating enum values. The Canada-specific framing implicitly excludes EU261/US DOT cases, but the description never states that boundary or names an alternative for other jurisdictions, so the when-not guidance is missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources